Modulation and Pulse Shaping Filter Classification of Raw Baseband Samples Based on Convolutional Neural Network

The convolutional neural network (CNN) is a machine learning methodology that was successfully implemented in many domains, including electromagnetics and wireless communications. This paper investigates the use of CNN in modulation and pulse shaping filter classification, which can be used in future cognitive radios to facilitate the reception of unknown signals. The focus of this paper is on the conversion of raw baseband samples to a format which complies with the CNN input. The AlexNet CNN architecture was selected and trained on six different datasets. Obtained results show that CNN can be used to classify modulation schemes and the raised cosine filter roll-off factor in noisy samples even without carrier synchronization.